Papers › Bridging the Gap: Examining Vision Foundation Models for Optical and Radio Astronomy...

Bridging the Gap: Examining Vision Foundation Models for Optical and Radio Astronomy Applications

17 Sep 2024arXiv:2409.11175links table onlyarchive 2025-07-28

E. Lastufka, O. Bait, M. Drozdova, V. Kinakh, D. Piras, M. Audard, M. Dessauges-Zavadsky, T. Holotyak, D. Schaerer, S. Voloshynovskiy

The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.

Vision foundation models, which have demonstrated significant potential in many multimedia applications, are often underutilized in the natural sciences. This is primarily due to mismatches between the nature of domain-specific scientific data and the typical training data used for foundation models, leading to distribution shifts. Scientific data often differ substantially in structure and characteristics, and researchers frequently face the challenge of optimizing model performance with limited labeled data of only a few hundred or thousand images. This work evaluates the performance of vision foundation models in astrophysics, with a focus on identifying the best practices for adapting them to domain-specific datasets. We aim to establish a framework for selecting, fine-tuning, and optimizing these models for common tasks in optical and radio astronomy. We compared multiple foundation models, including self-supervised, weakly supervised, and distillation-based architectures, across two representative optical and radio datasets. Experiments involved different fine-tuning strategies, projector heads, and data preprocessing techniques, with performance evaluated on classification and detection metrics. Features extracted by specific foundation models improved classification accuracy for optical galaxy images compared to conventional supervised training. Similarly, these models achieved equivalent or superior performance in object detection tasks with radio images. However, classification performance for radio galaxy images was generally poor, often falling short of supervised approaches. These findings demonstrate that vision foundation models can be effectively adapted to astrophysical applications, provided practitioners iterate on model selection, training strategies, and data handling.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 13 ran (11 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

elastufka/fm4astro officialmentioned in paperpytorchGPL-3.0Syntology: 16 samples, 13 ran (2 instrument-failed) · 3 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
8ran
3unverified

Licence: 16 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from elastufka/fm4astro. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

elastufka/fm4astro official repository 16 samples, 13 ran (2 instrument-failed) · 3 unverified
collate_fn in 500 papers finetune.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 1344900d0c914026 · report fixture: signature batch:list/1/tuple · returned dict · level recorded 2026-09-24
default_config evaluator.py ran GPL-3.0 (copyleft) · pointer only · f92f16a13cfc2e6a · report fixture: signature output_dir:str/0/str, arch:str/0/str, ep:int/0/int, all:bool/0/bool · returned dict · level recorded 2026-09-24
eval_binary classifier_model.py ran GPL-3.0 (copyleft) · pointer only · 3a7b80e5682f8cd3 · report fixture: signature test_loader:list/1/tuple, model:callable/0/?, device:str/0/str, metrics:list/1/NoneType, return_vals:bool/0/bool, n_classes:int/0/int · returned list · level recorded 2026-09-24
fit_pca evaluator.py ran fingerprinted GPL-3.0 (copyleft) · pointer only · ba8c7028bbbe7a67 · report fixture: signature data:ndarray/2/float, labels:ndarray/1/int, n_components:int/0/int · returned tuple · level recorded 2026-09-24
freeze_resnet_layers train_frcnn.py ran GPL-3.0 (copyleft) · pointer only · af9597222f43fdd4 · report fixture: signature model:callable/0/?, nlayers:int/0/int, unfreeze_first_block:bool/0/bool · returned MinimalModel · level recorded 2026-09-24
get_all_configs downstream.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 662e84e65de78e84 · report fixture: signature config:dict/0/? · returned list · level recorded 2026-09-24
get_last_layer classifier_model.py ran GPL-3.0 (copyleft) · pointer only · a4eaddefa2df529e · report fixture: signature model:callable/0/?, train_loader:list/1/tuple, device:str/0/str · returned tuple · level recorded 2026-09-24
jpg_loader fm_datasets.py ran · honoured contract GPL-3.0 (copyleft) · pointer only · 038de18b9aae0811 · report fixture: signature path:str/0/str · returned JpegImageFile · level recorded 2026-09-24
norm_label evaluator.py ran · violated contract fingerprinted GPL-3.0 (copyleft) · pointer only · 1291d15dae744bb4 · report fixture: signature lab:ndarray/1/float · returned ndarray · level recorded 2026-09-24
npy_loader fm_datasets.py ran · honoured contract GPL-3.0 (copyleft) · pointer only · 797d7b61a53aa714 · report fixture: signature path:str/0/str · returned ndarray · level recorded 2026-09-24
resize_boxes myGRCNNtransform.py ran GPL-3.0 (copyleft) · pointer only · d0fdd2f3703ea795 · report fixture: signature boxes:Tensor/2/float, original_size:list/1/int, new_size:list/1/int · returned Tensor · level recorded 2026-09-24
resize_keypoints myGRCNNtransform.py ran GPL-3.0 (copyleft) · pointer only · 76024c7f5ea7c958 · report fixture: signature keypoints:Tensor/3/float, original_size:list/1/int, new_size:list/1/int · returned Tensor · level recorded 2026-09-24
train_and_eval_model classifier_model.py ran GPL-3.0 (copyleft) · pointer only · 4709fd173194e4ad · report fixture: signature model:callable/0/?, train_loader:list/1/tuple, test_loader:list/1/tuple, criterion:callable/0/?, optimizer:SGD/0/?, eval_fn:callable/0/?, n_epochs:int/0/int, n_eval:int/0/int, device:str/0/str, verbose:bool/0/bool, keep_best_acc:bool/0/bool, class_names:list/1/str, confmat:bool/0/bool · returned tuple · level recorded 2026-09-24
create_model in 163 papers fasterrcnn_resnet18.py unverified GPL-3.0 (copyleft) · pointer only · 0d4c7f84fc4fb4ad · report
freeze_ViT_blocks train_frcnn.py unverified GPL-3.0 (copyleft) · pointer only · 8ad5e131c9f9151f · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections